Skip to main navigation Skip to search Skip to main content

MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference

  • Akshat Sharma
  • , Hangliang Ding
  • , Jianping Li
  • , Neel Dani
  • , Minjia Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

State-of-the-art 2-bit KV cache quantization techniques achieve excellent results in accelerating LLM inference while retaining accuracy on long context tasks. However, further pushing the compression ratio fails to deliver performance gains. In this work, we revisit these approaches by considering, additionally, adaptive KV methods that retain LLM accuracy with only a subset of KV states. This leads us to propose a method based on 2-bit KV cache quantization with adaptive KV policies. In addition, we take an algorithm and system co-design approach by developing hardware-friendly kernels to accelerate LLM inference while making MiniKV compatible with existing memory-efficient attention techniques such as FlashAttention, effectively translating algorithmic improvements into system performance gains. Experiments on a wide range of long context tasks show that MiniKV effectively achieves >80% KV cache compression while retaining accuracy, outperforming state-of-the-art methods while achieving excellent latency, throughput, and memory consumption improvements in long context inference.

Original languageEnglish (US)
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationACL 2025
EditorsWanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar
PublisherAssociation for Computational Linguistics (ACL)
Pages18506-18523
Number of pages18
ISBN (Electronic)9798891762565
DOIs
StatePublished - 2025
Event63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025 - Vienna, Austria
Duration: Jul 27 2025Aug 1 2025

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025
Country/TerritoryAustria
CityVienna
Period7/27/258/1/25

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference'. Together they form a unique fingerprint.

Cite this